Global contrast based salient region detection

Ming-Ming Cheng,  Niloy J. Mitra,  Xiaolei Huang,  Philip H. S. Torr,  Shi-Min Hu

Abstract

Automatic estimation of salient object regions across images, without any prior assumption or knowledge of the contents of the corresponding scenes, enhances many computer vision and computer graphics applications. We introduce a regional contrast based salient object extraction algorithm, which simultaneously evaluates global contrast differences and spatial weighted coherence scores. The proposed algorithm is simple, efficient, naturally multi-scale, and produces full-resolution, high-quality saliency maps. These saliency maps are further used to initialize a novel iterative version of GrabCut for high quality salient object segmentation. We extensively evaluated our algorithm using traditional salient object detection datasets, as well as a more challenging Internet image dataset. Our experimental results demonstrate that our algorithm consistently outperforms existing salient object detection and segmentation methods, yielding higher precision and better recall rates. We also show that our algorithm can be used to efficiently extract salient object masks from Internet images, enabling effective sketch-based image retrieval (SBIR) via simple shape comparisons. Despite such noisy internet images, where the saliency regions are ambiguous, our saliency guided image retrieval achieves a superior retrieval rate compared with state-of-the-art SBIR methods, and additionally provides important target object region information.

Papers

Most related projects on this website:

  • Efficient Salient Region Detection with Soft Image Abstraction. Ming-Ming Cheng, Jonathan Warrell, Wen-Yan Lin, Shuai Zheng, Vibhav Vineet, Nigel Crook. IEEE International Conference on Computer Vision (IEEE ICCV), 2013. [pdf] [Project page] [bib] [latex] [official version]
  • BING: Binarized Normed Gradients for Objectness Estimation at 300fp, Ming-Ming Cheng, Ziming Zhang, Wen-Yan Lin, Philip H. S. Torr, IEEE International Conference on Computer Vision and Pattern Recognition (IEEE CVPR), 2014. [Project page][pdf][bib] (Oral, Accept rate: 5.75%)
  • SalientShape: Group Saliency in Image Collections. Ming-Ming Cheng, Niloy J. Mitra, Xiaolei Huang, Shi-Min Hu. The Visual Computer 30 (4), 443-453, 2014. [pdf] [Project page] [bib] [latex] [Official version]

Downloads

Some files are zip format with password. Read the notes to see how to get the password.

1. Data

The MSRA10K benchmark dataset (a.k.a. THUS10000) comprises of per-pixel ground truth annotation for 10, 000 MSRA images (181 MB), each of which has an unambiguous salient object and the object region is accurately annotated with pixel wise ground-truth labeling (13.1M). We provide saliency maps (5.3 GB containing 170, 000 image) for our methods as well as other 15 state of the art methods, including FT [1], AIM [2], MSS [3], SEG [4], SeR [5], SUN [6], SWD [7], IM [8], IT [9], GB [10], SR [11], CA [12], LC [13], AC [14], and CB [15]. Saliency segmentation (71.3MB) results for FT[1], SEG[4], and CB[10] are also available.

2. Windows executable

We supply an windows msi for install our prototype software, which includes our implementation for FT[2], SR[14], LC[28], our HC, RC and saliency cut method.

3. C++ source code

The C++ implementation of our paper as well as several other state of the art works.

4. Supplemental material

Supplemental materials (647 MB) including comparisons with other 15 state of the art algorithms are now available.

Salient object detection results for images with multiple objects. We tested it on the dataset provided by the CVPR 2007 paper: “Image Segmentation by Probabilistic Bottom-Up Aggregation and Cue Integration”.

5. More results for recent methods

If anyone want to share their results on our MSRA10K benchmark (facilitate other researchers to compare with recent methods), please contact me via email (see the header image of this project page for it). I will put your results as well as paper links in this page.

Comparisons with state of the art methods

Figure. Statistical comparison results of (a) different saliency region detection methods, (b) their variants, and (c) object of interest region segmentation methods, using largest public available dataset (i) and (ii) our MSRA10K dataset (to be made public available). We compare our HC method and RC method with 15 state of art methods, including FT [1], AIM [2], MSS [3], SEG [4], SeR [5], SUN [6], SWD [7], IM [8], IT [9], GB [10], SR [11], CA [12], LC [13], AC [14], and CB [15]. We also take simple variable-size Gaussian model ‘Gau’ and GrabCut method as a baseline. (Please see our paper for detailed explaintions)

Figure. Comparison of average Fβ for different saliency segmentation methods: FT [1], SEG [4], and ours, on THUR15K dataset, which is composed by non-selected internet images.
Method IT AIM IM MSS SEG SeR SUN SWD CB
Time (s) 0.611 4.288 0.991 0.106 4.921 1.019 1.116 0.100 5.568
Code Matlab Matlab Matlab Matlab Matlab Matlab Matlab Matlab M&C
Method GB SR FT AC CA LC HC RC
Time (s) 1.614 0.064 0.102 0.109 53.1 0.018 0.019 0.254
Code Matlab Matlab C++ Matlab Matlab C++ C++ C++

Table. Average time taken to compute a saliency map for images in the MSRA10K database. (Note that we use the authors original implementations for MSS and FT, which is not well optimized code.)

Method Time(s) Code Type
FT 0.247 Matlab
SEG 7.48 M&C
CB 36.5 M&C
Our 0.621 C++

Table. Comparison of average time for different saliency segmentation methods.

Figure. Saliency maps computed by different state-of-the-art methods~(b-p), and with our proposed HC~(q) and RC methods~(r). Most results highlight edges, or are of low resolution. See also the shared data for saliency detection results for the whole MSRA10K dataset.

Figure. Sketch based image comparison. In each group from left to right, first column shows images download from Flickr using the corresponding keyword; second column shows our retrieval results obtained by comparing user input sketch with SaliencyCut result using shape context measure [41]; third column shows corresponding sketch based retrieval results using SHoG [42].

Figure. Illustration of results comparison for all images in the evaluation dataset. All results for 17 salient object detection methods and 10K images in MSRA10K dataset could be found in the supplemental materials (647 MB pdf, containing 200,000 images!).  Source code for generating such illustration could be found here:  CmIllustr::Imgs(…);

FAQs

Until now, more than 2000+ readers (according to email records) have request to get the source code for this project. Some of them have questions about using the code. Here are some frequently asked questions (some of them are frequently asked questions from many reviewers as well) for new users to refer:

Q1: I’m confused with the sentence in the paper: “In our experiments, the threshold is chosen empirically to be the threshold that gives 95% recall rate in our fixed thresholding experiments”. But all most the case, people have not the ground truth, so cannot compute the call rate. When I use your Cut application, I need to guess threshold value to have good cut image.

A: The recall rate is just used to evaluate the algorithm. When you use it, you typically don’t have to evaluate the algorithm itself very often. This sentence is used to explain what the fixed threshold we use typically means. Actually, when initialized using RC saliency maps, this threshold is 70 with saliency values normalized to [0,255]. It doesn’t mean that the saliency values corresponds to recall rate of 95% for every image, but empirically corresponds to recall rate of 95% for a large number of images. So, just use the suggested threshold of 70 is OK.

Q2: I use your code to get results for the same database you used. But the results seem to have some small difference from yours.

A: It seems that the cvtColor function in OpenCV 1.x is different from those in OpenCv 2.X. I suggest users to use those in recent versions. The segmentation method I used sometimes generates strange results, leading to strange results of saliency maps. This happens at low frequency. When this happens, I rerun the exe again and it becomes OK. I don’t know why, but this really happens when I use the exe first time after compiling (Very strange, maybe because some default initializations). If someone find the bug, please report to me.

Q3: Does your algorithm only get good results for images with single salient object? 

A: Mostly yes. As described in our paper, our method is suitable for images with an unambiguous saliency object. Since saliency detection methods typically have no prior knowledge about the target object, thus is very difficult. Much recent researches focus on images with single saliency object. Even for this simple case, state of the art algorithm may also fail. It’s understandable since supervised object detection which uses a large number of training data and prior knowledge also fails in many cases.

However, the value of saliency detection methods lies on their applications in many fields. Because they don’t need large human annotation for learning, and typically much faster than object detection methods, it’s possible to automatically process a large number of images with low cost. Although many of the saliency detection results may be wrong (up to 60% for noise internet image) because of the ambiguous or even missing of salient objects, we can still use efficient algorithms to select those good results and use them in many interesting applications like (Notes: all following projects use our saliency source code, with initial version of SaliencyCut used in our own Sketch2Photo project. Click here for a list of 1900+ citations to the PAMI 2015 (CVPR11) paper):

  1. Unsupervised joint object discovery and segmentation in internet images, M. Rubinstein, A. Joulin, J. Kopf, and C. Liu, in IEEE CVPR, 2013, pp. 1939–1946. (Used the proposed saliency measure and showed that saliency-based segmentation produces state-of-the-art results on co-segmentation benchmarks, without using co-segmentation!)
  2. Image retrieval: Sketch2Photo: Internet Image Montage. Tao Chen, Ming-Ming Cheng, Ping Tan, Ariel Shamir, Shi-Min Hu. ACM SIGGRAPH Asia. 28, 5, 124:1-10, 2009.
  3. SalientShape: Group Saliency in Image Collections. Ming-Ming Cheng, Niloy J. Mitra, Xiaolei Huang, Shi-Min Hu. The Visual Computer, 2013
  4. PoseShop: Human Image Database Construction and Personalized Content Synthesis. Tao Chen, Ping Tan, Li-Qian Ma, Ming-Ming Cheng, Ariel Shamir, Shi-Min Hu. IEEE TVCG, 19(5), 824-837, 2013.
  5. Internet visual media processing: a survey with graphics and vision applications, Tao Chen, Ping Tan, Li-Qian Ma, Ming-Ming Cheng, Ariel Shamir, Shi-Min Hu. The Visual Computer, 2013, 1-13.
  6. Image editing: Semantic Colorization with Internet Images, Yong Sang Chia, Shaojie Zhuo, Raj Kumar Gupta, Yu-Wing Tai, Siu-Yeung Cho, Ping Tan, Stephen Lin, ACM SIGGRAPH Asia. 2011.
  7. View selection: Web-Image Driven Best Views of 3D Shapes. The Visual Computer, 2011. Accepted. H Liu, L Zhang, H Huang
  8. Image Collage: Arcimboldo-like Collage Using Internet Images.ACM SIGGRAPH Asia, 30(6), 2011. H Huang, L Zhang, HC Zhang
  9. Image manipulation: Data-Driven Object Manipulation in Images. Chen Goldberg, Eurographics 2012, T Chen, FL Zhang, A Shamir, SM Hu.
  10. Saliency For Image Manipulation, R. Margolin, L. Zelnik-Manor, and A. Tal, Computer Graphics International (CGI) 2012.
  11. Mobile Product Search with Bag of Hash Bits and Boundary Reranking,  Junfeng He, Xianglong Liu, Tao Cheng, Jinyuan Feng, Tai-Hsu Lin, Hyunjin Chung and Shih-Fu Chang, IEEE CVPR, 2012.
  12. Unsupervised Object Discovery via Saliency-Guided Multiple Class Learning, Jun-Yan Zhu, Jiajun Wu, Yichen Wei, Eric Chang, and Zhuowen Tu, IEEE CVPR, 2012.
  13. Saliency Detection via Divergence Analysis: A Unified Perspective, ICPR 2012 (Best student paper). (The authors of this ICPR paper have derived that our formulation on global saliency has a deep connection with an information-theoretic measure, the so called Cauchy-Schwarz divergence.)
  14. Much more: http://scholar.google.com/scholar?cites=9026003219213417480

Q4: I’m confused about the definition of saliency. Why the annotation format (isolated points, binary mask regions, and bounding boxes) in different benchmarks for evaluating saliency detection methods are so different?

There are 3 different saliency detection directions: i) fixation prediction, ii) salient object detection, iii) objectness estimation. They have very different research target and very different applications. Personally, I’m mainly interested in the last two problems and will discuss them in a bit more detail.

Eye fixation models aims at predicting where human looks, i.e. a small set of fixation points. The most famous method in this area is Itti’s work in PAMI 1998. The MIT benchmark is designed for evaluating such methods.

Salient object detection, as what is done in this work, aim at finding most salient object in a scene and segment the whole extent of that object. The output is typically a single saliency map (or figure-ground segmentation). The advantages and disadvantages are described in detail in Q3. High precision is a major focus of our work, as we can use shape matching based technique to effectively select good segmentations and build robust applications on top. Most widely used benchmark for evaluating this problem is MSRA1000, which precisely segment 1000 salient objects in MSRA images. Our method achieves 93% precision and 90% recall on MSRA1000 (previous best reported results: 75% precision and 83% recall). Since our results on MSRA100 are mostly comparable to ground truth annotations, we need more challenging benchmark. MSRA10K and THUR15K are built for this purpose.

Objectness estimation is another attractive direction. These methods aim at proposing a small set (typically 1000) of bounding boxes to improve efficiency of classical sliding window pipeline. High recallat a small set of bounding box proposals is a major target. PASCAL VOC is a standard dataset for evaluating this problem. Using purely bottom up data driven methods to produce a single saliency map, as what is done in most salient object detection model, is less likely to succeed in this very challenging dataset. State of the art objectness proposal methods (PAMI12IJCV13) achieves 90+% recall on challenging PASCAL VOC dataset given a relatively small (e.g. 1000) number of bounding boxes, while been computational efficient (4 seconds per image). This is especially useful for speed up multi-class object detection problem, as each classifier only need to examine a much smaller number of image windows (e.g. 1,000,000 -> 1,000).

Q5: In nearly all 300+ papers citing this work, the F-Measure of RC method used for comparison is significantly lower than that is reported in this paper. Why?

Our salient object segmentation involves a powerful SaliencyCut method, for which we have not yet release the source code (will be released only after the journal version been published). The high performance of our salient object segmentation method could simply be verified by running our published binary code. When reporting the F-Measure of our method, most papers use adaptive threshold to get segmentation results, which produce much worse results than our original version. This is somehow reasonable and make the comparison easier, as they don’t have access to our SaliencyCut code. Notice that our method achieves 92% F-Measure on MSRA benchmark, and I have not yet see any other method get F-Measure better than 90% (achieved by our CVPR11 version).  It’s worth mentioning that even latest GrabCut method only achieves ‘comparable’ performance (F-Measure – 89%) on the same benchmark (see “Grabcut in One Cut, Meng Tang, Lena Gorelick, Olga Veksler, Yuri Boykov, ICCV, 2013″).

Q6: The benchmarks you use all have center bias, will this be a problem?

Regarding to the center bias, this seems to be a nature bias in real-world images. In the community of salient object detection, most methods tries to detect the most dominate object rather than dealing with complicated images, where many objects exist and have complicated occlusions, etc. Even (only) dealing with these simple (‘Flickr like’) images is also quite useful for many applications (see Q3). Even trained on thousands of accurately labeled images, state of the art object detection methods still can’t get robust results for PASCAL VOC like images. For salient object detection algorithms, the robustness could come from automatic selection of good results from thousands of images, for which we can get automatic segmentation results for free (no needs for training data annotation). See ‘SalientShape: Group Saliency in Image Collections’ for un-selected and automatic downloaded Flickr images dataset (also have clear center bias) as well as aforementioned applications.

Links to source code of other methods

FT [1] R. Achanta, S. Hemami, F. Estrada, and S. Susstrunk,“Frequency-tuned salient region detection,” in IEEE CVPR, 2009, pp. 1597–1604.
AIM [2] N. Bruce and J. Tsotsos, “Saliency, attention, and visual search: An information theoretic approach,” Journal of Vision, vol. 9, no. 3, pp. 5:1–24, 2009.
MSS [3] R. Achanta and S. S ¨ usstrunk, “Saliency detection using maximum symmetric surround,” in IEEE ICIP, 2010, pp. 2653–2656.
SEG [4] E. Rahtu, J. Kannala, M. Salo, and J. Heikkila, “Segmenting salient objects from images and videos,” ECCV, pp. 366–379, 2010.
SeR [5] H. Seo and P. Milanfar, “Static and space-time visual saliency detection by self-resemblance,” Journal of vision, vol. 9, no. 12, pp. 15:1–27, 2009.
SUN [6] L. Zhang, M. Tong, T. Marks, H. Shan, and G. Cottrell, “SUN: A bayesian framework for saliency using natural statistics,” Journal of Vision, vol. 8, no. 7, pp. 32:1–20, 2008.
SWD [7] L. Duan, C. Wu, J. Miao, L. Qing, and Y. Fu, “Visual saliency detection by spatially weighted dissimilarity,” in IEEE CVPR, 2011, pp. 473–480.
IM [8] N. Murray, M. Vanrell, X. Otazu, and C. A. Parraga, “Saliency estimation using a non-parametric low-level vision model,” in IEEE CVPR, 2011, pp. 433–440.
IT [9] L. Itti, C. Koch, and E. Niebur, “A model of saliency-based visual attention for rapid scene analysis,” IEEE TPAMI, vol. 20, no. 11, pp. 1254–1259, 1998.
GB [10] J. Harel, C. Koch, and P. Perona, “Graph-based visual saliency,” in NIPS, 2007, pp. 545–552.
SR [11] X. Hou and L. Zhang, “Saliency detection: A spectral residual approach,” in IEEE CVPR, 2007, pp. 1–8.
CA [12] S. Goferman, L. Zelnik-Manor, and A. Tal, “Context-aware saliency detection,” in IEEE CVPR, 2010, pp. 2376–2383.
LC [13] Y. Zhai and M. Shah, “Visual attention detection in video sequences using spatiotemporal cues,” in ACM Multimedia, 2006, pp. 815–824.
AC [14] R. Achanta, F. Estrada, P. Wils, and S. S ¨ usstrunk, “Salient region detection and segmentation,” in IEEE ICVS, 2008, pp. 66–75.
CB [15] H. Jiang, J. Wang, Z. Yuan, T. Liu, N. Zheng, and S. Li,“Automatic salient object segmentation based on context and shape prior,” in British Machine Vision Conference, 2011, pp. 1–12.
LP [16] T. Judd, K. Ehinger, F. Durand, A Torralba, Learning to predict where humans look, ICCV 2009.
Locations of visitors to this page
(Visited 97,587 times, 44 visits today)
  Subscribe  
Notify of
LANCHE
Guest
LANCHE

程老师,我调试了您关于图像显著性检测的相关代码,在评估算法时候,生成的.m文件在MATLAB上运行有错。
缺少这个函数xticklabel_rotate([1:5], 90, methodLabels, ‘interpreter’, ‘none’);
您能给我这个函数的实现代码吗?

LI
Guest
LI

请问你解决了吗,我也遇到同样的问题?

Sushil
Guest
Sushil

Hello.
I am trying to run the code in Visual Studio 2015.
I downloaded the code from provided GitHub page and ran the SaliencyMain.cpp in Visual Studio 2015 after changing the wkdir path.
It seems the Visual Studio 2015 throws a lot of error regarding CmLib as it suggests it to be old.

Please suggest in the comment below if someone has made the work and how?
Thank you.

Khimya
Guest
Khimya
Hello I am trying to run the VS project, It has worked once before for me, However it is now giving the following error >—— Build started: Project: SpRecoTOG14, Configuration: Release x64 —— 1> Moc’ing SpRecoUI.h… 1> The system cannot find the path specified. 1> Uic’ing SpRecoUI.ui… 1> The system cannot find the path specified. 1> Rcc’ing SpRecoUI.qrc… 1> The system cannot find the path specified. 1>C:\Program Files (x86)\MSBuild\Microsoft.Cpp\v4.0\V120\Microsoft.CppCommon.targets(170,5): error MSB6006: “cmd.exe” exited with code 3. ========== Build: 0 succeeded, 1 failed, 0 up-to-date, 0 skipped ========== While the Saliency project builds fine, I get the following error, while I… Read more »
Grace
Guest
Grace

I solve this trouble by create a folder named Lib,and put the CmLib.lib in it.But there is another question:error 0x000007b and 0x0000005.
Anyone know how to run it?

Sushil
Guest
Sushil

Did you use Visual Studio 2015 or other versions?

huangsenlin
Guest
huangsenlin

程老师,你好,我配置了qt的,编译也遇到了这个问题,
Moc’ing SpRecoUI.h…
1> 系统找不到指定的路径。
1> Uic’ing SpRecoUI.ui…
1> 系统找不到指定的路径。
1> Rcc’ing SpRecoUI.qrc…
1> 系统找不到指定的路径。
1>C:\Program Files (x86)\MSBuild\Microsoft.Cpp\v4.0\V110\Microsoft.CppCommon.targets(172,5): error MSB6006: “cmd.exe”已退出,代码为 3。
不知道为什么。期待您的回复,谢谢!

caryqr
Guest
caryqr

您好!我也遇到跟您一样的问题,请问您的问题有没有解决?能不能给我点指导,谢谢!

haojing
Guest
haojing

程老师,你好。编译SpRecoTOG14的时候,总提示
Moc’ing SpRecoUI.h…
1> 系统找不到指定的路径。
1> Uic’ing SpRecoUI.ui…
1> 系统找不到指定的路径。
1> Rcc’ing SpRecoUI.qrc…
1> 系统找不到指定的路径。
1>C:\Program Files (x86)\MSBuild\Microsoft.Cpp\v4.0\V110\Microsoft.CppCommon.targets(172,5): error MSB6006: “cmd.exe”已退出,代码为 3。
系统提示这几个文件被重命名、删除或移动。这是怎么回事?谢谢,期待您的回复。

laowang
Guest
laowang

同学,我也遇到同样的问题,你那个问题解决了吗?

huangsenlin
Guest
huangsenlin

同学你好,我最近也在学习这篇文章,很多东西都不懂,编译的时候遇到了跟你一样的问题,你解决了吗?

ZhangJingwei
Guest
ZhangJingwei

程老师,您好。我在配置这个Saliency项目时,编译通过了,却显示Uable to start program“………../Debug/CmLib.lib”,不知是什么原因?

李瑾
Guest
李瑾

请问,运行是总是显示无法打开文件“CmLibd.lib”,请问怎么解决的

lijnn
Guest
lijnn

您好,运行时无法打开CmLibed.lib,怎么解决,另外你用的qt是哪个版本的,谢谢了~

LSN
Guest
LSN

老师,您好,请问找不到CmLib.lib这个文件的问题您解决了么?

ZhangJingwei
Guest
ZhangJingwei

在CmLib项目里Saliency文件夹内的cpp文件显示无法打开StdAfx.h头文件

wd
Guest
wd

程老师您好,显著性的这个程序我都生成成功了,但是运行的时候出错,显示:”无法启动程序E:\saliency_cheng\CmCode-master\Release\CmLib.lib”这个问题怎么解决?我运行的时候运行的所有项目,CmLib.lib的生成链接也加到Saliency的附加库目录中了。

李瑾
Guest
李瑾

请问,运行是总是显示无法打开文件“CmLibd.lib”,请问怎么解决的

lijnn
Guest
lijnn

您好,运行时无法打开CmLibed.lib,怎么解决,另外你用的qt是哪个版本的,谢谢了~

Michaeljep
Guest
Michaeljep
Code promo PMU : 170 euros de bonus incluant 100€ de paris sportifs, 50 euros de paris hippiques et 20€ de poker. En plus, votre 1er dépôt sur les tables de poker sera doublé jusqu’à 500€ maximum. Ce code PMU est valable sur les Paris sportif, le Turf et le Poker Cliquez ici et indiquez le code : PMUPOKER Ce code promotionnel est à indiquer au moment de votre inscription sur PMU.fr à l’endroit ci-dessous. code promotionnel PMU PMU.fr est une plateforme de jeux en ligne qui convient à la fois aux amateurs de paris sportifs, de turf ou encore… Read more »
hongyi
Guest
hongyi

程老师,请问在我编译好Saliency这个程序后,要怎么使用呢?
我在cmd中输入Saliency后得到了这样的结果:F:\检测\CmCode-master\x64\Debug>Saliency

“Precision = -1.#IND, recall = -1.#IND, F-Measure = -1.#IND, intUnion = -1.#IND,mae = -1.#IND”

Zhang
Guest
Zhang

我也是遇见了这样的问题,请问您解决了吗
Precision = -1.#IND, recall = -1.#IND, F-Measure = -1.#IND, intUnion = -1.#IND,mae = -1.#IND

LIN
Guest
LIN

你好,我也碰到相同的问题。请问你解决了吗?

wang
Guest
wang

还有提到要下载的其他几个数据labeling (13.1M). saliency maps (5.3 GB )和segmentation (71.3MB) 链接均在“代码和数据”页面,而该页面只有aNYU,THUR15K (787MB),annotations (VOC 2007),MSRA10K:这4个数据,那相对应的分别是哪些呢?

wang
Guest
wang

程老师您好,我想用您的Global contrast based salient region detection 方法试试,但提到的数据10, 000 MSRA images打开链接后只有如下两个数据包,而没有10000的,是我找错了吗?
Image set A — 20,000 image labeled by three users. (images, labeled rectangles, and readme files)

Image set B — 5,000 images labeled by nine users. (images, labeled rectangles, and readme files)

毛思扬
Guest
毛思扬

程老师您好,上面所说提供的数据中,其中saliency maps (5.3 GB containing 170, 000 image) 我并没有在 “代码和数据” 页面中找到,请问是不再提供下载了吗?还是有其他方法可以下载的到?谢谢!期待您的回复。

瓦砾啦
Guest
瓦砾啦

程老师,请问下,召回率曲线图是通过生成的哪个文件绘制的?

瓦砾啦
Guest
瓦砾啦

请问绘制出的precision recall图,只有GC和RC的曲线,同样生成的显著图的FT,HC,SR等的曲线如何调出来

杨勇佳
Guest
杨勇佳

程老师你好 老师下载你的code压缩包 但是不知道解压密码

LiuFeng
Guest
LiuFeng

程老师您好
在调试的时候,总是出现这样的问题,在网上找了很多解决的方法,都没有奏效
C:\Program Files (x86)\MSBuild\Microsoft.Cpp\v4.0\V110\Microsoft.CppCommon.targets(134,5): error MSB3073: 命令“xcopy /y D:\VS2012\Self_write\ChengMM_Saliency Detection\x64\Debug\CmLibd.lib ..\..\Lib\
1>C:\Program Files (x86)\MSBuild\Microsoft.Cpp\v4.0\V110\Microsoft.CppCommon.targets(134,5): error MSB3073: :VCEnd”已退出,代码为 4。

我用的是vs2012+opencv2.4.9,solution中有5个工程,在生成解决方案时,4个成功1个失败